US12554842B2 - Malware detection in containerized environments - Google Patents
Malware detection in containerized environmentsInfo
- Publication number
- US12554842B2 US12554842B2 US17/809,586 US202217809586A US12554842B2 US 12554842 B2 US12554842 B2 US 12554842B2 US 202217809586 A US202217809586 A US 202217809586A US 12554842 B2 US12554842 B2 US 12554842B2
- Authority
- US
- United States
- Prior art keywords
- malware
- computing device
- deviation
- system calls
- program instructions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/55—Detecting local intrusion or implementing counter-measures
- G06F21/554—Detecting local intrusion or implementing counter-measures involving event detection and direct action
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/55—Detecting local intrusion or implementing counter-measures
- G06F21/56—Computer malware detection or handling, e.g. anti-virus arrangements
- G06F21/566—Dynamic detection, i.e. detection performed at run-time, e.g. emulation, suspicious activities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/03—Indexing scheme relating to G06F21/50, monitoring users, programs or devices to maintain the integrity of platforms
- G06F2221/034—Test or assess a computer or a system
Definitions
- the present disclosure relates to computer security, and more specifically, to anomaly and threat detection in micro-service computing environments.
- Anomaly and threat prevention and detection are generally of significant concern when pertaining to computer security and operations.
- active inspection of files, networks, and processes within a system searching for malware or malicious software reduces the likelihood of infectious code compromising the system in real-time.
- a malware detection method, system, and computer program for containerized environments includes monitoring, via a computing device, operation of a container image, the monitoring comprising receiving a plurality of system calls performed during the operation of the container image; comparing, via the computing device, the plurality of system calls to prior container behavior associated with previous operation of the container image; identifying, via the computing device, a deviation from the prior container behavior; and in response to identifying the deviation, isolating, via the computing device, a subset of the plurality of system calls and classifying the subset to a malware class of a plurality of malware classes including a confidence level.
- the method further includes generating an alert to notify of potential malware and at least one malware class of the plurality of malware classes in response to identifying the confidence level exceeding a pre-determined threshold.
- FIG. 1 illustrates a functional block diagram illustrating a malware detection environment according to at least one embodiment
- FIG. 2 depicts an example system configuration of malware feature extraction and classification according to at least one embodiment
- FIG. 3 depicts a simplified illustration of a malware decision tree according to at least one embodiment
- FIG. 4 illustrates an example of deviation identification of a malware detection system according to at least one embodiment
- FIG. 5 illustrates a flowchart depicting a process for malware detection, in accordance with an embodiment of the invention
- FIG. 6 depicts a block diagram illustrating components of the software application of FIG. 1 , in accordance with an embodiment of the invention
- FIG. 7 depicts a cloud-computing environment, in accordance with an embodiment of the present invention.
- FIG. 8 depicts abstraction model layers, in accordance with an embodiment of the present invention.
- embodiments of the present invention constitute a method
- a method is a process for execution by a computer, i.e. is a computer-implementable method.
- the various steps of the method therefore reflect various parts of a computer program, e.g. various parts of one or more algorithms.
- a system may be a single device or a collection of distributed devices that are adapted to execute one or more embodiments of the methods of the present invention.
- a system may be a personal computer (PC), a server or a collection of PCs and/or servers connected via a network such as a local area network, the Internet and so on to cooperatively execute at least one embodiment of the methods of the present invention.
- PC personal computer
- server or a collection of PCs and/or servers connected via a network such as a local area network, the Internet and so on to cooperatively execute at least one embodiment of the methods of the present invention.
- the following described exemplary embodiments provide a method, computer system, and computer program product for malware detection in containerized environments.
- Malware, ransomware, and other applicable security anomalies pose a significant threat to computer systems.
- Tactics such as machine learning for analysis of security anomalies have been utilized to circumvent exposure and vulnerability; however, both static and dynamic approaches have their various setbacks.
- approaches involving static analysis of security anomalies such as image analysis and policy-based detection fail to account for adapting to changing behaviors within the applicable system (e.g., new malwares which has not been encountered before, and cannot be actively searched for), and approaches involving dynamic analysis of security anomalies result in high false positive rates in which system instances/activities are misclassified as security anomalies.
- malware may require extraction of features derived from components of the system in order to accurately detect malware in which the detection is based upon a confidence score relative to maliciousness.
- Classification methods applied directly on all logged operations are generally effected by noise problems that impact classifying accuracy.
- the present embodiments have the capacity to detect malware within containerized environments in a manner that circumvents the aforementioned issues via vectorizing extracted features across containers by shrinking file paths and process paths utilizing optimal data structures, isolating processes identified within detected anomalies for determination of data subsets that deviate from normal activity within the containerized system, and classifying the data subsets as malware or benign; thus, reducing the malware false positive rate rendering malware detection within containerized environments feasible.
- FIG. 1 an environment for malware detection in containerized environments 100 is depicted according to an exemplary embodiment.
- FIG. 1 provides only an illustration of implementation and does not imply any limitations regarding the environments in which different embodiments may be implemented. Modifications to environment 100 may be made by those skilled in the art without departing from the scope of the invention as recited by the claims.
- environment 100 includes a server 120 communicatively coupled to a database 130 , a container orchestration module 140 , a malware collection module 150 , a malware classifications database 155 communicatively coupled to malware collection module 150 , a malware detection module 160 , and an anomaly detection database 165 communicatively coupled to malware detection module 160 , each of which are communicatively coupled over a network 110 .
- Network 110 may include various types of communication networks, such as a wide area network (WAN), local area network (LAN), a telecommunication network, a wireless network, a public switched network and/or a satellite network, cloud networks, etc. Some clouds are based upon non-traditional IP networks.
- network 110 may be embodied as a physical network and/or a virtual network.
- a physical network can be, for example, a physical telecommunications network connecting numerous computing nodes or systems such as computer servers and computer clients.
- a virtual network can, for example, combine numerous physical networks or parts thereof into a logical virtual network.
- numerous virtual networks can be defined over a single physical network.
- server 120 is configured to generate a centralized platform configured to allow users to view, add, and/or edit applicable data received by server 120 over network 110 from any applicable module described herein. For example, users may view the resulting false positive rate of the security anomalies detected within environment 100 .
- malware may incorporate any security anomalies including but not limited to trojans, ransomware, polymorphic malware, rootkits, keyloggers, bots, spyware/adware, viruses, worms, suspicious activity, or any other applicable security anomalies known to those of ordinary skill in the art.
- container orchestration module 140 manages “pods” which are configured to be applied to management of computing-intensive large scale task applications in network 110 .
- pods may function as groups of containers (e.g., rkt container, runc, OCI, etc.) that share network 110 along with computing resources of environment 100 for the purpose of hosting one or more application instances.
- container orchestration module 140 may manage a plurality of virtual machine pods, namespace pods, or any other applicable type of deployable objects known to those of ordinary skill in the art.
- Container orchestration module 140 takes one or more images that contain applications, respective dependencies, and a small Operating System (OS) distribution in a layered filesystem, and it creates a process within its own namespaces on a hardware node.
- container orchestration module 140 includes at any applicable container orchestration system for automation of efforts to execute containerized workloads and services, including automation of software deployment in cloud environments, scale of software in cloud environments, and management of software in cloud environments.
- Malware collection module 150 is configured to run a plurality of malwares derived from a plurality of families, and tracks system calls relating to files, network, and processes of the pods operated by container orchestration module 140 , performs feature-selection and train a classifier that given a vector representation of a program within container orchestration module 140 , to classify it as benign or malicious.
- the classification can also include the malware family along with confidence.
- the one or more models may be summarizations of the behavior associated with one or more container images. For example, interactions between the container images and the filesystems, processes, and/or network may be reflected in the one or more models.
- malware collection module 150 one of the purposes of malware collection module 150 is to efficiently collect a plurality of malware features and/or malware-related features derived from the system calls, in which the system calls may be encoded into the one or more models.
- the collection of malware features is initiated by malware collection module 150 monitoring all applicable invoked system calls and selecting those that pertain to files, network, and processes related to the container images and/or associated sources thereof. Continuous monitoring of the operations of the container image allows a plurality of system calls performed during operation of the container image to be collected and recorded.
- One purpose of malware collection module 150 is to assist malware detection module 160 by creating feature candidates via selecting accessed file paths, creating process paths, and source/destination ports.
- malware collection module 150 is designed to shrink file paths and process paths in a manner in which each resulted feature will be frequent across the plurality of malwares classes based on predefined parameters. Malware collection module 150 distinguishes between infectious programs and benign programs by utilizing at least one subset of data used to train the one or more models in order to identify features indicative of benign software.
- the malware features support malware detection module 160 comparing the plurality of system calls to prior behavior associated with container image operations. For example, extraction of malware features may be accomplished via malware collection module 150 running malware separately across a plurality of malware classes in which malware collection module 150 effectively records and generalizes the plurality of systems calls allowing malware collection module 150 to apply various mechanisms disclosed herein to filter out system calls common for benign software. In some embodiments, extraction of malware features is performed offline in which the malware features are configured to be stored in anomaly detection database 165 .
- Malware detection module 160 is designed to identify deviations from learned behavior associated with the one or more models in real-time, in which each deviation is a suspicious event/activity.
- malware detection module 160 identifies deviations by assigning vectors of suspicious activity (hereinafter “deviation vectors”) in which the vectors are binary and represent operations the container image has done before and operations the container image has not done before.
- device vectors vectors of suspicious activity
- Malware detection module 160 identifies deviations in which deviations as described herein are elements of the behavior of a program that may be classified via vectorization.
- malware detection module 160 determines which files and/or directories of the container image are desired to be processed, the amount of network communication necessary, system call configurations, etc.
- malware detection module 160 classifies the malware features due to the fact that some deviations may be considered “regular” deviations in that they are derived from stable behaviors that ultimately contribute to the false positive rate.
- Classification of the malware features allows representation of container image behavior as malware feature vectors providing distinction between that which is malware and that which is benign.
- malware collection module 150 may generate one or more clusters of the malware feature vectors which supports filtration of the benign features from the malicious features.
- identifying deviations requires malware detection module 160 utilizing an isolation process in order to isolate each suspicious process, along with associated processes, derived from the operations of the container image.
- Continuous processing by malware collection module 150 and malware detection module 160 allows the development of an accumulating run-time profile relating to the monitored behavior of the containers derived from container orchestration module 140 .
- the run time profile is designed to represent patterns that appear in both the plurality of malware and the monitored application associated with the applicable containers derived from container orchestration module 140 .
- Configuration 200 includes a plurality of executing software application 210 - 1 , 210 - 2 , up to 210 -N (collectively 210 , hereinafter referred to as “applications”) of container orchestration module 140 including a plurality of filesystems, processes, and/or networks 220 - 1 , 220 - 2 , up to 220 -N (collectively 220 , hereinafter referred to as “files”) including files, folders, metadata, tables, and any other applicable data structure and/or data known to those of ordinary skill in the art.
- Configuration 200 further includes a modeling module 230 communicatively coupled to server 120 , container orchestration module 140 , malware collection module 150 , and/or malware detection module 160 .
- Modeling module 230 includes a classifier 240 , a feature extractor 250 communicatively coupled to malware collection module 150 , and a feature database 260 communicatively coupled to classifier 240 .
- modeling module 230 is a machine learning module configured to use one or more heuristics and/or machine learning based models for performing one or more of the various aspects as described herein.
- the machine learning based models may be performed using a wide variety of methods or combinations of methods, such as supervised learning, unsupervised learning, temporal difference learning, reinforcement learning and so forth.
- supervised learning which may be used with the present technology include AODE (averaged one-dependence estimators), artificial neural network, back propagation, Bayesian statistics, naive bays classifier, Bayesian network, Bayesian knowledge base, case-based reasoning, decision trees, inductive logic programming, Gaussian process regression, gene expression programming, group method of data handling (GMDH), learning automata, learning vector quantization, minimum message length (decision trees, decision graphs, etc.), lazy learning, instance-based learning, nearest neighbor algorithm, analogical modeling, probably approximately correct (PAC) learning, ripple down rules, a knowledge acquisition methodology, symbolic machine learning algorithms, sub symbolic machine learning algorithms, support vector machines, random forests, ensembles of classifiers, bootstrap aggregating (bagging), boosting (meta-algorithm), ordinal classification, regression analysis, information fuzzy networks (IFN), statistical classification, linear classifiers, fisher's linear discriminant, logistic regression, perceptron, support vector machines, quadratic classifiers, k-nearest
- AODE
- unsupervised learning which may be used with the present technology include artificial neural network, data clustering, expectation-maximization, self-organizing map, radial basis function network, vector quantization, generative topographic map, information bottleneck method, IBSEAD (distributed autonomous entity systems based interaction), association rule learning, apriori algorithm, eclat algorithm, FP-growth algorithm, hierarchical clustering, single-linkage clustering, conceptual clustering, partitional clustering, k-means algorithm, fuzzy clustering, and reinforcement learning.
- temporal difference learning may include Q-learning and learning automata. Specific details regarding any of the examples of supervised, unsupervised, temporal difference or other machine learning described in this paragraph are known and are considered to be within the scope of this disclosure.
- a plurality of system calls that impact the process lifecycle and/or interact with applications 210 and files 220 of the applicable executing container image are analyzed by malware collection module 150 allowing modeling module 230 to embed a sequence of system calls derived from the plurality of system calls into one or more machine learned models.
- the applicable model processing the sequence of system calls is compared to a behavior model generated by modeling module 230 , in which the behavior model is generated from container images of container orchestration module 140 associated with applications 210 and files 220 .
- the purpose of the behavior model is to not only provide a reference metric for behavior within containers, but also to support system call telemetry analysis of containers.
- the one or more models generated my modeling module 230 may include various datasets and be utilized for various purposes. Outputs of one model may be utilized as a source of training data for another model, and deploying of models may support testing in a controlled environment before being deployed in a public setting for model optimization and system calls filtration purposes. Furthermore while malware collection module 150 is performing the monitoring of system calls, sets of byte codes (“n-grams”) or the relative frequency of occurrence of key byte-patterns relating to malware are continuously being identified via iterations of modeling module 230 and stored in anomaly detection database 165 for the purpose of training classifier 240 .
- n-grams sets of byte codes
- anomaly detection database 165 for the purpose of training classifier 240 .
- the plurality of malware classes are outputs of the classification model and may be predefined via server 120 and/or may be ascertained from outputs of the one or more models derived from iterations performed by modeling module 230 , such as but not limited to a classification model associated with classifier 240 .
- classifier 240 receives the malware feature vectors for the purpose of applying one of the plurality of malware classes, or a benign class if applicable, to each of the malware feature vectors and assigning a confidence to the malware feature vectors in which the confidence may be an output of classifier 240 .
- malware collection module 150 While malware collection module 150 is actively monitoring applications 210 and files 220 and modeling module 230 is performing iterations, malware collection module 150 is creating malware feature vectors by selecting all accessed file paths, created process paths, sources, and destination ports ascertainable from applications 210 and files 220 , and compressing the plurality of system calls of the monitored container image into the run-time profile.
- the shrinking of components of the operations of the container image is performed by malware collection module 150 being configured to shrink file paths and processes of applications 210 and files 220 in a manner in which each resulting malware feature is frequent across the plurality of malwares based on the predefined parameter.
- creation of feature candidates using various selection approaches naturally results in overfitting which would result in an abundant amount of false negatives.
- malware collection module 150 performs the aforementioned technique based on predefined parameters.
- the predefined parameters may be established via server 120 (e.g., user inputs on the centralized platform) or derived from outputs of the one or more models.
- malware collection module 150 performs filtration, feature selection, and clustering of the malware feature vectors through various cognitive operations such as, a frequency distribution of terms and key concepts using term-frequency-inverse document frequency (e.g., “Tf-idf”) vectors, and/or other term vector based similarity operations.
- Tf-idf is an operation that measures an importance of words in files 220 .
- the Tf-idf is a numerical statistic that is intended to reflect how important a word is to applications 210 and files 220 .
- malware collection module 150 performs clustering of the malwares based on the one or more similarities wherein the one or more similarities can be determined in terms of multiple measures including but not limited to Euclidean distance, Manhattan distance, dynamic time warping (DTW) distance, Minkowski Distance, Cosine distance, Correlation coefficients (e.g. Pearson, Spearman), or any other applicable similarity measure known to those of ordinary skill in the art.
- the choice of similarity measure generally depends on where clustering is applied.
- the clustering of malware may include one or more of K-means clustering or other centroid based clustering model, hierarchical clustering, distribution clustering models, density based clustering models such as, e.g., DBSCAN or OPTICS, HCS clustering, or neural network based models such as, e.g., self-organizing maps, or any other suitable clustering model.
- Malware detection module 160 having malware profile 420 allows malware detection module 160 to identify a plurality of deviations 420 due to the fact that malware profile 420 not only represents what is “normal behavior” for container images of container orchestration module 140 but also what is commonly attributed to the one or more malwares based on features F 1-N .
- plurality of deviations 430 are detected via malware detection module 160 comparing block level operations of environment 100 to the behavior model which is continuously being updated with both malicious and benign activity and in some instances suspicious activity. Detection of plurality of deviations 430 may be based on various measures including but not limited to ranges of values, bounded rationality, standard deviation, or any other applicable measurement of anomaly detection/determination known to those of ordinary skill in the art.
- Classifier 240 receives plurality of deviations 430 in a vector representation from malware detection module 160 in which modeling module 230 applies the label of one of malware classes C 1-N and the confidence to each of plurality of deviations 430 as outputs of the classification model. There is a desire for classifier 240 to solely be fed F 1-N rather than all monitored operations of the container image, in which selectivity of classifier 240 is imperative. Malware detection module 160 performs isolation of subsets of the plurality of system calls and feeds deviation vectors to classifier 240 for the purpose of classifier 240 applying malware classes C 1-N appropriately. In some embodiments, modeling module 230 supports malware detection module 160 performing isolation by applying heuristics in order to determine applicable processes associated with the malware within the deviation vectors.
- all applicable processes of operations may be identified based on the particular deviation within the deviation vector.
- This approach allows malware detection module 160 to select a plurality of deviation features and/or deviation-related features derived from the deviation vectors.
- the resulting deviation features are sent to classifier 240 for classification.
- the plurality of system calls are compared to prior container behavior associated with previous operations of the container image prior to the aforementioned isolation process, in which this prior container behavior is embodied in malware profile 420 .
- FIG. 5 depicts a flowchart 500 illustrating a computer-implemented method of malware detection, consistent with an illustrative embodiment.
- Process 500 is illustrated as a collection of blocks, in a logical flowchart, which represents a sequence of operations that can be implemented in hardware, software, or a combination thereof.
- the blocks represent computer-executable instructions that, when executed by one or more processors, perform the recited operations.
- computer-executable instructions may include routines, programs, objects, components, data structures, and the like that perform functions or implement abstract data types.
- the order in which the operations are described is not intended to be construed as a limitation, and any number of the described blocks can be combined in any order and/or performed in parallel to implement the process.
- malware collection module 150 generates feature candidates associated with the plurality of malware based on the monitoring performed in step 510 .
- malware collection module 150 generates a vector of features/malware vector representing instances of any of applications 210 .
- the vector may represent program behavior and in particular the presence of malware or lack thereof, in which each entry relates to a specific system call and the applicable value associated with the entry relates to a count of how many times the specific system call was executed across a time period.
- the malware feature vector are ascertained by utilizing an offline process to separately run malware across multiple classes, compress the systems calls, and filter out the system calls including benign elements.
- malware collection module 150 shrinks file paths and process paths associated with applications 210 in order to allow feature extractor 250 to begin the feature filtration process.
- Feature extractor 250 shrinks the file paths and process paths in a manner in which each of features F 1-N will be frequent across malware classes C 1-N .
- Tree 300 of FIG. 3 depicts a preferred approach towards accomplishing proper designation of features F 1-N across malware classes C 1-N in a manner which reduces noise.
- modeling module 230 performs clustering of the plurality of malware represented by the features obtained thus far.
- feature extractor 250 filters out features frequent for the plurality of malware and for benign programs as well, in which as previously mentioned any applicable clustering, grouping, and/or TF-IDF approaches may be applied to cluster the plurality of malware.
- the clustering is intended to output a resulting set of features derived from the feature vector in which the output is a union of the features for each cluster that remains after the filtration process.
- modeling module 230 trains classifier 240 in order for classifier 240 to perform classification of the malware.
- classifier 240 receives the applicable vector as an input and maps the vector to a confidence that the input belongs to one or more malware classes C 1-N , in which malware classes C 1-N pertain to the various malwares and/or benign programs.
- the classification can employ probabilistic and/or statistical-based analysis and a support vector machine (SVM) that can be an example of classifier 240 that can be employed.
- SVM support vector machine
- the malware feature vector is configured to be inserted into the classification model of modeling module 230 in order to map malware features F 1-N across malware classes C 1-N .
- the time period for monitoring and recording operations of the container image may be established by server 120 based upon malware collection module 150 indicating that there are no new system calls (e.g. no new container behavior exists) and that malware detection module 160 should terminate monitoring.
- malware detection module 160 should terminate monitoring.
- the classification model serves the purpose of not only determining if a detected anomaly is a result of malware running on the system without relying solely on the deviation, but also continuously checking the types of suspect malware in a logging manner to wait and see if the suspected malware is finally malware.
- server 120 and/or feature extractor 250 generates the run-time profile in order for malware detection module 160 to identify deviations from the normal behavior associated with the containers.
- the run-time profile is designed to represent a stored profile corresponding to patterns (e.g., behavior-related, data-related, etc.) detected within applications 210 and the plurality of malware.
- the run-time profile serves as a reference point specific to applications 210 based on the features.
- run profile allows for malware detection module 160 to detect features that are frequent in the plurality of malwares, rather than for all new activities within the respective monitored application.
- malware detection module 160 identifies the plurality of deviations from the monitored behavior associated with the container images.
- monitored “normal” behavior is defined as the behavior ascertained from the behavior model generated by modeling module 230 .
- the deviation identification process is rooted in malware detection module 160 identifying all the processes involved directly and/or indirectly with a particular deviation. For example, a first process A configured to create a second process B, which is designed to create a third process C may each has their respective system calls. At some period of time process C executes an action that has not been previously observed.
- Malware detection module 160 is configured to not only ascertain the source (e.g., applicable deviation feature) of the previously unobserved operation, but also perform a concept referred to as “isolation” in which malware detection module 160 analyzes the process tree-structure in the system and decides for each process whether it is related to the current deviated process or not. All operations performed by those related processes are aggregated to build the deviation vector. For each newly identified deviation, malware detection module 160 isolates all processes related to the applicable system call that performed the deviation, and sends all the related system calls of the aforementioned processes to classifier 240 .
- the isolation feature allows malware detection module 160 to not only isolate all system calls relevant to malware utilizing the aforementioned approaches, but also capture malware spawned from new processes based on an associated anomaly. For example, if a deviation is detected based upon deviation features then the related processes are isolated, resulting in only the operations associated with the related processes being sent in a deviation vector to the classification model.
- malware detection module 160 isolates processes associated with and/or derived from the deviation.
- malware may attempt to hide within normal acceptable operations.
- programs running within container orchestration module 140 are significantly more concrete and stable, but malware may still go undetected within this environment if reliance is based solely upon the detected deviations.
- malware detection module 160 relies on classifier 240 to detect malware associated with the deviations by transmitting to classifier 240 processes derived from deviations, potentially suspicious activity, and benign activity one at a time in an isolated manner. This allows for not only the reduction of noise, but also increased accuracy to malware detection.
- the deviation vector is transmitted to classifier 240 in which classifier 240 is able to apply applicable labels and confidence based upon probability of being malicious.
- isolation performed by malware detection module 160 allows for iterative classification by classifier 240 resulting in labeling of malwares that includes level of propensity based upon probability.
- optimization of applying the labels may be provided by server 120 requiring validation of classifications from users via inputs received on the centralized platform.
- malware detection module 160 determines whether the confidence associated with the applicable malware exceeds the predetermined threshold based upon the previous mapping performed by classifier 240 .
- the confidence of the deviation is a probability of a membership of the malware in one of the clusters.
- the confidence is configured to be generated by classifier 240 and includes a numerical value along with an indication of whether the input to the classification model belongs to at least one of the plurality of malware classes. If malware detection module 160 determines that the confidence does not exceed a predefined confidence threshold then malware detection module 160 returns to step 570 of process 500 and continues to identify deviations from the normal behavior.
- step 590 of process 500 occurs in which server 120 generates an alert configured to be presented to users via graphical interfaces on the centralized platform.
- the alert includes information pertaining to which class of the plurality of malware classes the particular malware belongs to, in which the alerting process based upon the aforementioned steps results in a significant amount of reduction of false alerts emitted by intrusion detection systems. It should be noted that the classification model outputting a “benign” classification may account for hidden false positives as well.
- the alerting is based upon the confidence level exceeding the predefined confidence threshold; however, the alerting requires a malware classification from the classification model in combination with a confidence level that exceeds the predefined confidence threshold in order to reduce the amount of false positives. For example, when a program has performed an operation that is an anomaly, malware detection module 160 has ascertained that the operation is popular among the malwares, and the sub-program responsible for the deviation also performed operations that in aggregation are inherent to some malware classes/families.
- FIG. 6 is a block diagram of components 600 of computers depicted in FIG. 1 in accordance with an illustrative embodiment of the present invention. It should be appreciated that FIG. 6 provides only an illustration of one implementation and does not imply any limitations with regard to the environments in which different embodiments may be implemented. Many modifications to the depicted environments may be made based on design and implementation requirements.
- Data processing system 602 , 604 is representative of any electronic device capable of executing machine-readable program instructions.
- Data processing system 602 , 604 may be representative of a smart phone, a computer system, PDA, or other electronic devices.
- Examples of computing systems, environments, and/or configurations that may represented by data processing system 602 , 604 include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, multiprocessor systems, microprocessor-based systems, network PCs, minicomputer systems, and distributed cloud computing environments that include any of the above systems or devices.
- the one or more servers may include respective sets of components illustrated in FIG. 6 .
- Each of the sets of components include one or more processors 602 , one or more computer-readable RAMs 608 and one or more computer-readable ROMs 610 on one or more buses 602 , and one or more operating systems 614 and one or more computer-readable tangible storage devices 616 .
- the one or more operating systems 614 and computing event management system 210 may be stored on one or more computer-readable tangible storage devices 616 for execution by one or more processors 602 via one or more RAMs 608 (which typically include cache memory).
- each of the computer-readable tangible storage devices 616 is a magnetic disk storage device of an internal hard drive.
- each of the computer-readable tangible storage devices 616 is a semiconductor storage device such as ROM 610 , EPROM, flash memory or any other computer-readable tangible storage device that can store a computer program and digital information.
- Each set of components 600 also includes a R/W drive or interface 614 to read from and write to one or more portable computer-readable tangible storage devices 608 such as a CD-ROM, DVD, memory stick, magnetic tape, magnetic disk, optical disk or semiconductor storage device.
- a software program, such as computing event management system 210 can be stored on one or more of the respective portable computer-readable tangible storage devices 608 , read via the respective RAY drive or interface 618 and loaded into the respective hard drive.
- Each set of components 600 may also include network adapters (or switch port cards) or interfaces 616 such as a TCP/IP adapter cards, wireless wi-fi interface cards, or 3G or 4G wireless interface cards or other wired or wireless communication links.
- Applicable software can be downloaded from an external computer (e.g., server) via a network (for example, the Internet, a local area network or other, wide area network) and respective network adapters or interfaces 616 . From the network adapters (or switch port adaptors) or interfaces 616 , the centralized platform is loaded into the respective hard drive 608 .
- the network may comprise copper wires, optical fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers.
- Each of components 600 can include a computer display monitor 620 , a keyboard 622 , and a computer mouse 624 .
- Components 600 can also include touch screens, virtual keyboards, touch pads, pointing devices, and other human interface devices.
- Each of the sets of components 600 also includes device processors 602 to interface to computer display monitor 620 , keyboard 622 and computer mouse 624 .
- the device drivers 612 , R/W drive or interface 618 and network adapter or interface 618 comprise hardware and software (stored in storage device 604 and/or ROM 606 ).
- Cloud computing is a model of service delivery for enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal management effort or interaction with a provider of the service.
- This cloud model may include at least five characteristics, at least three service models, and at least four deployment models.
- On-demand self-service a cloud consumer can unilaterally provision computing capabilities, such as server time and network storage, as needed automatically without requiring human interaction with the service's provider.
- Resource pooling the provider's computing resources are pooled to serve multiple consumers using a multi-tenant model, with different physical and virtual resources dynamically assigned and reassigned according to demand. There is a sense of location independence in that the consumer generally has no control or knowledge over the exact location of the provided resources but may be able to specify location at a higher level of abstraction (e.g., country, state, or datacenter).
- Rapid elasticity capabilities can be rapidly and elastically provisioned, in some cases automatically, to quickly scale out and rapidly released to quickly scale in. To the consumer, the capabilities available for provisioning often appear to be unlimited and can be purchased in any quantity at any time.
- Measured service cloud systems automatically control and optimize resource use by leveraging a metering capability at some level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported providing transparency for both the provider and consumer of the utilized service.
- level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts).
- SaaS Software as a Service: the capability provided to the consumer is to use the provider's applications running on a cloud infrastructure.
- the applications are accessible from various client devices through a thin client interface such as a web browser (e.g., web-based e-mail).
- a web browser e.g., web-based e-mail
- the consumer does not manage or control the underlying cloud infrastructure including network, servers, operating systems, storage, or even individual application capabilities, with the possible exception of limited user-specific application configuration settings.
- PaaS Platform as a Service
- the consumer does not manage or control the underlying cloud infrastructure including networks, servers, operating systems, or storage, but has control over the deployed applications and possibly application hosting environment configurations.
- Analytics as a Service the capability provided to the consumer is to use web-based or cloud-based networks (i.e., infrastructure) to access an analytics platform.
- Analytics platforms may include access to analytics software resources or may include access to relevant databases, corpora, servers, operating systems or storage.
- the consumer does not manage or control the underlying web-based or cloud-based infrastructure including databases, corpora, servers, operating systems or storage, but has control over the deployed applications and possibly application hosting environment configurations.
- IaaS Infrastructure as a Service
- the consumer does not manage or control the underlying cloud infrastructure but has control over operating systems, storage, deployed applications, and possibly limited control of select networking components (e.g., host firewalls).
- Private cloud the cloud infrastructure is operated solely for an organization. It may be managed by the organization or a third party and may exist on-premises or off-premises.
- Public cloud the cloud infrastructure is made available to the general public or a large industry group and is owned by an organization selling cloud services.
- Hybrid cloud the cloud infrastructure is a composition of two or more clouds (private, community, or public) that remain unique entities but are bound together by standardized or proprietary technology that enables data and application portability (e.g., cloud bursting for load-balancing between clouds).
- a cloud computing environment is service oriented with a focus on statelessness, low coupling, modularity, and semantic interoperability.
- An infrastructure comprising a network of interconnected nodes.
- cloud computing environment 700 comprises one or more cloud computing nodes 50 with which local computing devices used by cloud consumers, such as, for example, personal digital assistant (PDA) or cellular telephone 54 A, desktop computer 54 B, laptop computer 54 C, and/or automobile computer system 54 N may communicate.
- Nodes 50 may communicate with one another. They may be grouped (not shown) physically or virtually, in one or more networks, such as Private, Community, Public, or Hybrid clouds as described hereinabove, or a combination thereof.
- This allows cloud computing environment 700 to offer infrastructure, platforms and/or software as services for which a cloud consumer does not need to maintain resources on a local computing device.
- computing devices 54 A-N shown in FIG. 7 are intended to be illustrative only and that computing nodes 50 and cloud computing environment 700 can communicate with any type of computerized device over any type of network and/or network addressable connection (e.g., using a web browser).
- FIG. 8 a set of functional abstraction layers provided by cloud computing environment 700 ( FIG. 7 ) is shown. It should be understood in advance that the components, layers, and functions shown in FIG. 8 are intended to be illustrative only and embodiments of the invention are not limited thereto. As depicted, the following layers and corresponding functions are provided:
- Hardware and software layer 60 includes hardware and software components.
- hardware components include: mainframes 61 ; RISC (Reduced Instruction Set Computer) architecture based servers 62 ; servers 63 ; blade servers 64 ; storage devices 65 ; and networks and networking components 66 .
- software components include network application server software 66 and database software 68 .
- Virtualization layer 60 provides an abstraction layer from which the following examples of virtual entities may be provided: virtual servers 61 ; virtual storage 62 ; virtual networks 63 , including virtual private networks; virtual applications and operating systems 64 ; and virtual clients 65 .
- management layer 80 may provide the functions described below.
- Resource provisioning 81 provides dynamic procurement of computing resources and other resources that are utilized to perform tasks within the cloud computing environment.
- Metering and Pricing 82 provide cost tracking as resources are utilized within the cloud computing environment, and billing or invoicing for consumption of these resources. In one example, these resources may include application software licenses.
- Security provides identity verification for cloud consumers and tasks, as well as protection for data and other resources.
- User portal 83 provides access to the cloud computing environment for consumers and system administrators.
- Service level management 84 provides cloud computing resource allocation and management such that required service levels are met.
- Service Level Agreement (SLA) planning and fulfillment 85 provide pre-arrangement for, and procurement of, cloud computing resources for which a future requirement is anticipated in accordance with an SLA.
- SLA Service Level Agreement
- Workloads layer 90 provides examples of functionality for which the cloud computing environment may be utilized. Examples of workloads and functions which may be provided from this layer include: mapping and navigation 91 ; software development and lifecycle management 92 ; virtual classroom education delivery 93 ; data analytics processing 94 ; and transaction processing 95 .
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Virology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Claims (20)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US17/809,586 US12554842B2 (en) | 2022-06-29 | 2022-06-29 | Malware detection in containerized environments |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US17/809,586 US12554842B2 (en) | 2022-06-29 | 2022-06-29 | Malware detection in containerized environments |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| US20240004993A1 US20240004993A1 (en) | 2024-01-04 |
| US12554842B2 true US12554842B2 (en) | 2026-02-17 |
Family
ID=89433107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US17/809,586 Active 2043-03-11 US12554842B2 (en) | 2022-06-29 | 2022-06-29 | Malware detection in containerized environments |
Country Status (1)
| Country | Link |
|---|---|
| US (1) | US12554842B2 (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7509244B2 (en) * | 2021-01-20 | 2024-07-02 | 日本電信電話株式会社 | GENERATION APPARATUS, GENERATION METHOD, AND GENERATION PROGRAM |
| US12585760B2 (en) * | 2022-07-28 | 2026-03-24 | Pure Storage, Inc. | Monitoring for security threats in a container system |
| US20240184858A1 (en) * | 2022-12-05 | 2024-06-06 | Applied Materials, Inc. | Methods and mechanisms for automatic sensor grouping to improve anomaly detection |
| US12608485B2 (en) | 2022-12-29 | 2026-04-21 | Netapp, Inc. | Enhancing container security by performing container vulnerability reduction based on library and/or function removal and system call blocking |
| US20240256690A1 (en) * | 2023-01-31 | 2024-08-01 | Malwarebytes Inc. | Intelligent cloud storage security |
| US12321450B2 (en) * | 2023-03-02 | 2025-06-03 | Bitdefender IPR Management Ltd. | Antimalware systems and methods using optimal triggering of artificial intelligence modules |
| US12468809B2 (en) * | 2023-04-07 | 2025-11-11 | Crowdstrike, Inc. | Applying diffusion models in adversarial purification and adversarial sample generation in cybersecurity |
| US12518012B2 (en) * | 2023-10-19 | 2026-01-06 | Google Llc | Structure-aware neural networks for malware detection |
| CN118070287B (en) * | 2024-04-18 | 2024-07-19 | 广州锦高信息科技有限公司 | Method and system for preventing Lecable virus invasion |
Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7069594B1 (en) * | 2001-06-15 | 2006-06-27 | Mcafee, Inc. | File system level integrity verification and validation |
| US8375450B1 (en) * | 2009-10-05 | 2013-02-12 | Trend Micro, Inc. | Zero day malware scanner |
| US20150295945A1 (en) * | 2014-04-14 | 2015-10-15 | Drexel University | Multi-Channel Change-Point Malware Detection |
| US20160173516A1 (en) * | 2013-11-07 | 2016-06-16 | Cyberpoint International Llc | Methods And Systems For Malware Detection |
| US20170063890A1 (en) | 2015-08-31 | 2017-03-02 | Splunk Inc. | Rarity analysis in network security anomaly/threat detection |
| US20170251003A1 (en) * | 2016-02-29 | 2017-08-31 | Palo Alto Networks, Inc. | Automatically determining whether malware samples are similar |
| US20170262633A1 (en) | 2012-09-26 | 2017-09-14 | Bluvector, Inc. | System and method for automated machine-learning, zero-day malware detection |
| US9794287B1 (en) | 2016-10-31 | 2017-10-17 | International Business Machines Corporation | Implementing cloud based malware container protection |
| US20190163901A1 (en) * | 2017-11-29 | 2019-05-30 | Institute For Information Industry | Computer device and method of identifying whether container behavior thereof is abnormal |
| US10397255B1 (en) * | 2015-09-23 | 2019-08-27 | StackRox, Inc. | System and method for providing security in a distributed computation system utilizing containers |
| US10607011B1 (en) * | 2015-07-21 | 2020-03-31 | Fatih Orhan | Method to detect zero-day malware applications using dynamic behaviors |
| US20200162483A1 (en) * | 2018-11-16 | 2020-05-21 | Accenture Global Solutions Limited | Malware detection |
| US20200193016A1 (en) * | 2018-12-13 | 2020-06-18 | Beijing Jingdong Shangke Information Technology Co., Ltd. | System and method for container file integrity monitoring |
| US20200296117A1 (en) * | 2019-03-13 | 2020-09-17 | Microsoft Technology Licensing, Llc | Cloud security using multidimensional hierarchical model |
| US20210105613A1 (en) * | 2019-10-08 | 2021-04-08 | The United States Of America As Represented By The Secretary Of The Navy | System and Method for Aggregated Machine Learning on Indicators of Compromise on Mobile Devices |
| US20210117544A1 (en) * | 2018-06-28 | 2021-04-22 | Crowdstrike, Inc. | Analysis of Malware |
| CN112905421A (en) | 2021-03-18 | 2021-06-04 | 中科九度(北京)空间信息技术有限责任公司 | Container abnormal behavior detection method of LSTM network based on attention mechanism |
| US20210263779A1 (en) * | 2018-11-08 | 2021-08-26 | Intel Corporation | Function as a service (faas) system enhancements |
| US20220129551A1 (en) * | 2020-10-23 | 2022-04-28 | Sophos Limited | File integrity monitoring |
| US20220292196A1 (en) * | 2021-03-12 | 2022-09-15 | Commvault Systems, Inc. | Detecting ransomware in monitored data |
| US20230028394A1 (en) * | 2020-01-05 | 2023-01-26 | British Telecommunications Public Limited Company | Code-based malware detection |
| US20230090689A1 (en) * | 2020-02-25 | 2023-03-23 | Siemens Aktiengesellschaft | Analysis of a Container Instance of an Operating System |
| US20230105087A1 (en) * | 2021-10-01 | 2023-04-06 | Secureworks Corp. | Systems and methods for detecting malicious hands-on-keyboard activity via machine learning |
| US20230124166A1 (en) * | 2021-10-15 | 2023-04-20 | Dell Products L.P. | Application programming interface anomaly detection |
-
2022
- 2022-06-29 US US17/809,586 patent/US12554842B2/en active Active
Patent Citations (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7069594B1 (en) * | 2001-06-15 | 2006-06-27 | Mcafee, Inc. | File system level integrity verification and validation |
| US8375450B1 (en) * | 2009-10-05 | 2013-02-12 | Trend Micro, Inc. | Zero day malware scanner |
| US20170262633A1 (en) | 2012-09-26 | 2017-09-14 | Bluvector, Inc. | System and method for automated machine-learning, zero-day malware detection |
| US20160173516A1 (en) * | 2013-11-07 | 2016-06-16 | Cyberpoint International Llc | Methods And Systems For Malware Detection |
| US20150295945A1 (en) * | 2014-04-14 | 2015-10-15 | Drexel University | Multi-Channel Change-Point Malware Detection |
| US10607011B1 (en) * | 2015-07-21 | 2020-03-31 | Fatih Orhan | Method to detect zero-day malware applications using dynamic behaviors |
| US20170063890A1 (en) | 2015-08-31 | 2017-03-02 | Splunk Inc. | Rarity analysis in network security anomaly/threat detection |
| US10397255B1 (en) * | 2015-09-23 | 2019-08-27 | StackRox, Inc. | System and method for providing security in a distributed computation system utilizing containers |
| US20170251003A1 (en) * | 2016-02-29 | 2017-08-31 | Palo Alto Networks, Inc. | Automatically determining whether malware samples are similar |
| US9794287B1 (en) | 2016-10-31 | 2017-10-17 | International Business Machines Corporation | Implementing cloud based malware container protection |
| US20190163901A1 (en) * | 2017-11-29 | 2019-05-30 | Institute For Information Industry | Computer device and method of identifying whether container behavior thereof is abnormal |
| US20210117544A1 (en) * | 2018-06-28 | 2021-04-22 | Crowdstrike, Inc. | Analysis of Malware |
| US20210263779A1 (en) * | 2018-11-08 | 2021-08-26 | Intel Corporation | Function as a service (faas) system enhancements |
| US20200162483A1 (en) * | 2018-11-16 | 2020-05-21 | Accenture Global Solutions Limited | Malware detection |
| US20200193016A1 (en) * | 2018-12-13 | 2020-06-18 | Beijing Jingdong Shangke Information Technology Co., Ltd. | System and method for container file integrity monitoring |
| US20200296117A1 (en) * | 2019-03-13 | 2020-09-17 | Microsoft Technology Licensing, Llc | Cloud security using multidimensional hierarchical model |
| US20210105613A1 (en) * | 2019-10-08 | 2021-04-08 | The United States Of America As Represented By The Secretary Of The Navy | System and Method for Aggregated Machine Learning on Indicators of Compromise on Mobile Devices |
| US20230028394A1 (en) * | 2020-01-05 | 2023-01-26 | British Telecommunications Public Limited Company | Code-based malware detection |
| US20230090689A1 (en) * | 2020-02-25 | 2023-03-23 | Siemens Aktiengesellschaft | Analysis of a Container Instance of an Operating System |
| US20220129551A1 (en) * | 2020-10-23 | 2022-04-28 | Sophos Limited | File integrity monitoring |
| US20220292196A1 (en) * | 2021-03-12 | 2022-09-15 | Commvault Systems, Inc. | Detecting ransomware in monitored data |
| CN112905421A (en) | 2021-03-18 | 2021-06-04 | 中科九度(北京)空间信息技术有限责任公司 | Container abnormal behavior detection method of LSTM network based on attention mechanism |
| US20230105087A1 (en) * | 2021-10-01 | 2023-04-06 | Secureworks Corp. | Systems and methods for detecting malicious hands-on-keyboard activity via machine learning |
| US20230124166A1 (en) * | 2021-10-15 | 2023-04-20 | Dell Products L.P. | Application programming interface anomaly detection |
Non-Patent Citations (6)
| Title |
|---|
| Mell et al., "The NIST Definition of Cloud Computing", National Institute of Standards and Technology, Special Publication 800-145, Sep. 2011, pp. 1-7. |
| Tunde-Onadele, "A Study on Container Vulnerability Exploit Detection," 2019 IEEE International Conference on Cloud Engineering (IC2E), IEEE Xplore, pp. 121-126, <https://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&queryText=A%20Study%20on%20Container%20Vulnerability%20Exploit%20Detection>. |
| Zhang, et al., "A Real-time Intrusion Detection System Based on OC-SVM for Containerized Applications," 2021 IEEE 24th International Conference on Computational Science and Engineering (CSE 2021), IEEE Xplore, pp. 138-145, <https://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&queryText=A%20real-time%20intrusion%20detection%20system%20based%20on%20OC-SVM%20for%20containerized%20applications>. |
| Mell et al., "The NIST Definition of Cloud Computing", National Institute of Standards and Technology, Special Publication 800-145, Sep. 2011, pp. 1-7. |
| Tunde-Onadele, "A Study on Container Vulnerability Exploit Detection," 2019 IEEE International Conference on Cloud Engineering (IC2E), IEEE Xplore, pp. 121-126, <https://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&queryText=A%20Study%20on%20Container%20Vulnerability%20Exploit%20Detection>. |
| Zhang, et al., "A Real-time Intrusion Detection System Based on OC-SVM for Containerized Applications," 2021 IEEE 24th International Conference on Computational Science and Engineering (CSE 2021), IEEE Xplore, pp. 138-145, <https://ieeexplore.ieee.org/search/searchresult.jsp?newsearch=true&queryText=A%20real-time%20intrusion%20detection%20system%20based%20on%20OC-SVM%20for%20containerized%20applications>. |
Also Published As
| Publication number | Publication date |
|---|---|
| US20240004993A1 (en) | 2024-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240004993A1 (en) | Malware detection in containerized environments | |
| US11954568B2 (en) | Root cause discovery engine | |
| US11165806B2 (en) | Anomaly detection using cognitive computing | |
| CN112602081B (en) | Enhance network security and operational monitoring with alert confidence assignments | |
| Baldwin et al. | Leveraging support vector machine for opcode density based detection of crypto-ransomware | |
| US20190258648A1 (en) | Generating asset level classifications using machine learning | |
| US20220188690A1 (en) | Machine learning security threat detection using a meta-learning model | |
| WO2022179441A1 (en) | Standardization in the context of data integration | |
| US12055998B2 (en) | Intelligent grouping of events in computing system event and computing system incident management domains | |
| US11093320B2 (en) | Analysis facilitator | |
| US11620407B2 (en) | Real-time, context based detection and classification of data | |
| US12293393B2 (en) | Predictive service orchestration using threat modeling analytics | |
| US9842219B1 (en) | Systems and methods for curating file clusters for security analyses | |
| US20260057089A1 (en) | Modular cybersecurity engine in a data intelligence system | |
| US12265614B2 (en) | Label recommendation for cybersecurity content | |
| US11921676B2 (en) | Analyzing deduplicated data blocks associated with unstructured documents | |
| US11900106B2 (en) | Personalized patch notes based on software usage | |
| US12147554B2 (en) | Contextualization of organization data and handling storage quantification | |
| US11762896B2 (en) | Relationship discovery and quantification | |
| US11893132B2 (en) | Discovery of personal data in machine learning models | |
| US20260004121A1 (en) | Iterative data processing optimization engine in a data intelligence system | |
| KR20200065683A (en) | An apparatus for classify log massage to patterns | |
| De Amorim et al. | Partitional clustering of malware using k-means | |
| US12360854B2 (en) | Dynamic policy creation and adhoc backups using data criticality | |
| US12476977B2 (en) | Network user permission prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| AS | Assignment |
Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW YORK Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:ROZENBERG, BORIS;SAGRON, YEHOSHUA;GREENBERG, LEV;SIGNING DATES FROM 20220628 TO 20220629;REEL/FRAME:060349/0927 |
|
| FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE AFTER FINAL ACTION FORWARDED TO EXAMINER |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: ADVISORY ACTION MAILED |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION COUNTED, NOT YET MAILED |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE AFTER FINAL ACTION FORWARDED TO EXAMINER |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: ALLOWED -- NOTICE OF ALLOWANCE NOT YET MAILED Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT RECEIVED Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
| STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
| STCF | Information on status: patent grant |
Free format text: PATENTED CASE |